INTERPRETING A MEANING OF A WORD STRING

• US 20190325027A1
• Filed: 04/16/2019
• Published: 10/24/2019
• Est. Priority Date: 04/19/2018
• Status: Active Grant

• Current Assignee: Entigenlogic LLC
• Original Assignee: Entigenlogic LLC
• Inventors: Williams, Frank John, Lazzara, David Ralph, Wurzel, Donald Joseph, Thompson, Paige Kristen, Sundberg, Stephen Emerson, Chen, Stephen, Knutson, Karl Olaf, Thomas, Jessy, Corns, II, David Michael, Chu, Andrew, Faurie, Eric Andrew, Mazurkiewicz, Theodore, Grube, Gary W.
• Granted Patent: US 11,321,530 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

A method includes obtaining a string of words and determining whether two or more words of the string of words are in a word group. When the two or more words are in the word group, the method further includes retrieving a set of word group identigens for the word group and retrieving sets of word identigens for remaining words of the string of words. The method further includes determining whether a word group identigen of the set of word group identigens and word identigens of the sets of word identigens creates an entigen group that is a valid interpretation of the string of words. When the entigen group is the valid interpretation of the string of words, the method further includes outputting the entigen group.

Claims

1. A method for execution by a computing device, the method comprises:

obtaining a string of words;

determining whether two or more words of the string of words are in a word group; and

when the two or more words are in the word group;

retrieving a set of word group identigens for the word group;

retrieving a plurality of sets of word identigens for remaining words of the string of words;

determining whether a word group identigen of the set of word group identigens and a plurality of word identigens of the plurality of sets of word identigens creates an entigen group that is a valid interpretation of the string of words; and

when the entigen group is the valid interpretation of the string of words, outputting the entigen group.

2. The method of claim 1, wherein the determining whether two or more words of the string of words are in a word group further comprises:

detecting that a first word of the two or more words of the string of words matches a first entry word of one or more word group entries of a word group list, wherein each word group entry of the word group list includes two or more entry words and an entry set of word group identigens that corresponds to interpretations of the two or more entry words, wherein the two or more entry words of each of the one or more word group entries includes the first entry word;

determining, for at least some of the one or more word group entries, whether remaining words of the of the two or more words of the string of words match remaining entry words of the two or more entry words; and

when the remaining words of the of the two or more words of the string of words match the remaining entry words of the two or more entry words of a matching word group entry of the at least some of the one or more word group entries, indicating that the two or more words of the string of words are in the word group.

3. The method of claim 1, wherein the determining whether two or more words of the string of words are in a word group further comprises:

comparing the two or more words of the string of words to a word group entry of a word group list, wherein the word group entry of the word group list includes two or more entry words and an entry set of word group identigens that corresponds to potential interpretations of the two or more entry words; and

indicating that the two or more words of the string of words are in the word group when the two or more words of the string of words compare favorably to the two or more entry words of the entry of the word group list.

4. The method of claim 1, wherein the determining whether the word group identigen of the set of word group identigens and the plurality of word identigens of the plurality of sets of word identigens creates the entigen group that is the valid interpretation of the string of words further comprises:

interpreting, based on a knowledge database, the set of word group identigens and the plurality of sets of word identigens to produce an intermediate identigen group, wherein the intermediate identigen group is potentially a most likely interpretation of the string of words, wherein each intermediate identigen of the intermediate identigen group corresponds to a selected identigen of one of the set of word group identigens and the plurality of word identigens of the plurality of sets of word identigens, wherein each selected identigen represents a most likely meaning of one of the two or more words of the string of words and one remaining word of the string of words, wherein the knowledge database includes a plurality of records that link meanings of words having a connected meaning;

determining whether the intermediate identigen group includes one selected word group identigen of the set of word group identigens;

determining whether the intermediate identigen group includes a subset of intermediate identigens corresponding to the plurality of sets of word identigens, wherein the remaining words of the string of words corresponds to the subset of intermediate identigens;

determining whether a sequencing of each intermediate identigen is in accordance with identigen sequencing rules of the knowledge database; and

when the intermediate identigen group includes one selected word group identigen of the set of word group identigens and the intermediate identigen group includes the subset of intermediate identigens that correspond to the plurality of sets of word identigens and the sequencing of each intermediate identigen is in accordance with the identigen sequencing rules of the knowledge database;

generating the entigen group that is the valid interpretation of the string of words utilizing the intermediate identigen group.

5. The method of claim 4 further comprises:

when;

the intermediate identigen group does not include one selected word group identigen of the set of word group identigens;

or

the intermediate identigen group does not include the subset of intermediate identigens that correspond to the plurality of sets of word identigens;

or

the sequencing of each intermediate identigen is not in accordance with the identigen sequencing rules of the knowledge database;

obtaining an updated plurality of sets of word identigens for all words of the string of words;

interpreting, based on the knowledge database, the updated plurality of sets of word identigens to produce the entigen group, wherein the entigen group is a most likely interpretation of the string of words, wherein each entigen of the entigen group corresponds to a selected word identigen of the updated plurality of sets of word identigens, wherein each selected word identigen represents a most likely meaning of a word of the string of words; and

indicating that the entigen group is the valid interpretation of the string of words.

6. A computing device of a computing system, the computing device comprises:

an interface;

a local memory; and

a processing module operably coupled to the interface and the local memory, wherein the processing module functions to;

obtain, via the interface, a string of words;

determine whether two or more words of the string of words are in a word group; and

when the two or more words are in the word group;

retrieve, via the interface, a set of word group identigens for the word group;

retrieve, via the interface, a plurality of sets of word identigens for remaining words of the string of words;

determine whether a word group identigen of the set of word group identigens and a plurality of word identigens of the plurality of sets of word identigens creates an entigen group that is a valid interpretation of the string of words; and

when the entigen group is the valid interpretation of the string of words, output, via the interface, the entigen group.

7. The computing device of claim 6, wherein the processing module further functions to determine whether two or more words of the string of words are in the word group by:

detecting that a first word of the two or more words of the string of words matches a first entry word of one or more word group entries of a word group list, wherein each word group entry of the word group list includes two or more entry words and an entry set of word group identigens that corresponds to interpretations of the two or more entry words, wherein the two or more entry words of each of the one or more word group entries includes the first entry word;

determining, for at least some of the one or more word group entries, whether remaining words of the of the two or more words of the string of words match remaining entry words of the two or more entry words; and

when the remaining words of the of the two or more words of the string of words match the remaining entry words of the two or more entry words of a matching word group entry of the at least some of the one or more word group entries, indicating that the two or more words of the string of words are in the word group.

8. The computing device of claim 6, wherein the processing module further functions to determining whether two or more words of the string of words are in the word group by:

comparing the two or more words of the string of words to a word group entry of a word group list, wherein the word group entry of the word group list includes two or more entry words and an entry set of word group identigens that corresponds to potential interpretations of the two or more entry words; and

indicating that the two or more words of the string of words are in the word group when the two or more words of the string of words compare favorably to the two or more entry words of the entry of the word group list.

9. The computing device of claim 6, wherein the processing module further functions to determine whether the word group identigen of the set of word group identigens and the plurality of word identigens of the plurality of sets of word identigens creates the entigen group that is the valid interpretation of the string of words by:

interpreting, based on a knowledge database, the set of word group identigens and the plurality of sets of word identigens to produce an intermediate identigen group, wherein the intermediate identigen group is potentially a most likely interpretation of the string of words, wherein each intermediate identigen of the intermediate identigen group corresponds to a selected identigen of one of the set of word group identigens and the plurality of word identigens of the plurality of sets of word identigens, wherein each selected identigen represents a most likely meaning of one of the two or more words of the string of words and one remaining word of the string of words, wherein the knowledge database includes a plurality of records that link meanings of words having a connected meaning;

determining whether the intermediate identigen group includes one selected word group identigen of the set of word group identigens;

determining whether the intermediate identigen group includes a subset of intermediate identigens corresponding to the plurality of sets of word identigens, wherein the remaining words of the string of words corresponds to the subset of intermediate identigens;

determining whether a sequencing of each intermediate identigen is in accordance with identigen sequencing rules of the knowledge database; and

when the intermediate identigen group includes one selected word group identigen of the set of word group identigens and the intermediate identigen group includes the subset of intermediate identigens that correspond to the plurality of sets of word identigens and the sequencing of each intermediate identigen is in accordance with the identigen sequencing rules of the knowledge database;

generating the entigen group that is the valid interpretation of the string of words utilizing the intermediate identigen group.

10. The computing device of claim 9, wherein the processing module further functions to:

when;

the intermediate identigen group does not include one selected word group identigen of the set of word group identigens;

or

the intermediate identigen group does not include the subset of intermediate identigens that correspond to the plurality of sets of word identigens;

or

the sequencing of each intermediate identigen is not in accordance with the identigen sequencing rules of the knowledge database;

obtain, via the interface, an updated plurality of sets of word identigens for all words of the string of words;

interpret, based on the knowledge database, the updated plurality of sets of word identigens to produce the entigen group, wherein the entigen group is a most likely interpretation of the string of words, wherein each entigen of the entigen group corresponds to a selected word identigen of the updated plurality of sets of word identigens, wherein each selected word identigen represents a most likely meaning of a word of the string of words; and

indicate that the entigen group is the valid interpretation of the string of words.

11. A computer readable memory comprises:

a first memory element that stores operational instructions that, when executed by a processing module, causes the processing module to;

obtain a string of words; and

determine whether two or more words of the string of words are in a word group; and

a second memory element that stores operational instructions that, when executed by the processing module, causes the processing module to;

when the two or more words are in the word group;

retrieve a set of word group identigens for the word group;

retrieve a plurality of sets of word identigens for remaining words of the string of words;

determine whether a word group identigen of the set of word group identigens and a plurality of word identigens of the plurality of sets of word identigens creates an entigen group that is a valid interpretation of the string of words; and

when the entigen group is the valid interpretation of the string of words, output the entigen group.

12. The computer readable memory of claim 11, wherein the processing module functions to execute the operational instructions stored by the first memory element to cause the processing module to determine whether two or more words of the string of words are in the word group by:

detecting that a first word of the two or more words of the string of words matches a first entry word of one or more word group entries of a word group list, wherein each word group entry of the word group list includes two or more entry words and an entry set of word group identigens that corresponds to interpretations of the two or more entry words, wherein the two or more entry words of each of the one or more word group entries includes the first entry word;

determining, for at least some of the one or more word group entries, whether remaining words of the of the two or more words of the string of words match remaining entry words of the two or more entry words; and

when the remaining words of the of the two or more words of the string of words match the remaining entry words of the two or more entry words of a matching word group entry of the at least some of the one or more word group entries, indicating that the two or more words of the string of words are in the word group.

13. The computer readable memory of claim 11, wherein the processing module functions to execute the operational instructions stored by the first memory element to cause the processing module to determine whether two or more words of the string of words are in the word group by:

comparing the two or more words of the string of words to a word group entry of a word group list, wherein the word group entry of the word group list includes two or more entry words and an entry set of word group identigens that corresponds to potential interpretations of the two or more entry words; and

indicating that the two or more words of the string of words are in the word group when the two or more words of the string of words compare favorably to the two or more entry words of the entry of the word group list.

14. The computer readable memory of claim 11, wherein the processing module functions to execute the operational instructions stored by the second memory element to cause the processing module to determine whether the word group identigen of the set of word group identigens and the plurality of word identigens of the plurality of sets of word identigens creates the entigen group that is the valid interpretation of the string of words by:

interpreting, based on a knowledge database, the set of word group identigens and the plurality of sets of word identigens to produce an intermediate identigen group, wherein the intermediate identigen group is potentially a most likely interpretation of the string of words, wherein each intermediate identigen of the intermediate identigen group corresponds to a selected identigen of one of the set of word group identigens and the plurality of word identigens of the plurality of sets of word identigens, wherein each selected identigen represents a most likely meaning of one of the two or more words of the string of words and one remaining word of the string of words, wherein the knowledge database includes a plurality of records that link meanings of words having a connected meaning;

determining whether the intermediate identigen group includes one selected word group identigen of the set of word group identigens;

determining whether the intermediate identigen group includes a subset of intermediate identigens corresponding to the plurality of sets of word identigens, wherein the remaining words of the string of words corresponds to the subset of intermediate identigens;

determining whether a sequencing of each intermediate identigen is in accordance with identigen sequencing rules of the knowledge database; and

when the intermediate identigen group includes one selected word group identigen of the set of word group identigens and the intermediate identigen group includes the subset of intermediate identigens that correspond to the plurality of sets of word identigens and the sequencing of each intermediate identigen is in accordance with the identigen sequencing rules of the knowledge database;

generating the entigen group that is the valid interpretation of the string of words utilizing the intermediate identigen group.

15. The computer readable memory of claim 14 further comprises:

the second memory element further stores operational instructions that, when executed by the processing module, causes the processing module to;

when;

the intermediate identigen group does not include one selected word group identigen of the set of word group identigens;

or

the intermediate identigen group does not include the subset of intermediate identigens that correspond to the plurality of sets of word identigens;

or

the sequencing of each intermediate identigen is not in accordance with the identigen sequencing rules of the knowledge database;

obtain an updated plurality of sets of word identigens for all words of the string of words;

interpret, based on the knowledge database, the updated plurality of sets of word identigens to produce the entigen group, wherein the entigen group is a most likely interpretation of the string of words, wherein each entigen of the entigen group corresponds to a selected word identigen of the updated plurality of sets of word identigens, wherein each selected word identigen represents a most likely meaning of a word of the string of words; and

indicate that the entigen group is the valid interpretation of the string of words.